Study of structured light based 3-D vision inspection using RBF neural network

Based on the radial based function (RBF) neural network, a method of structured light based 3-D vision inspection is presented. This method uses the RBF ANN (artificial neural network) to establish the mapping relationship between a world coordinate system and an image coordinate system. Compared with general methods, it ignores the vision modeling error, and also allows the existence of the optical adjustment error. It overcomes the disadvantages of general methods efficiently, and ensures the inspection system to have much high measurement accuracy.